© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44443
    Prev
    Next
    INDEX
    Explanations

    continental breakfast

    np_acts-logits-general · gemini-2.5-flash-lite

    only or just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deja
    0.49
     tarses
    0.45
     pyruvate
    0.45
     centrif
    0.43
     niobium
    0.42
     evaluation
    0.42
     instar
    0.41
    콧
    0.41
    섭
    0.41
    क्ष्म
    0.40
    POSITIVE LOGITS
     केवळ
    0.52
     केवल
    0.50
     इकोनॉ
    0.47
     नहीं
    0.46
    edian
    0.44
     Were
    0.43
     త
    0.43
     কেবল
    0.43
     Belong
    0.42
    并不
    0.42
    Activations Density 0.000%

    No Known Activations